Intelligent Image Classifier with KNN

This n8n workflow provides an automated solution for image classification using the K-Nearest Neighbors (KNN) algorithm. It begins by generating embeddings for your input images using a state-of-the-art multimodal model. These embeddings are then used to query a Qdrant vector database, retrieving the closest matches from a pre-indexed dataset of landscape images. A majority vote mechanism is employed to determine the most likely landscape category, with a tie-breaking mechanism that intelligently expands the search radius if necessary. This ensures robust and accurate classification, even for ambiguous cases, making it ideal for organizing and understanding large image collections.